aws-neuron
/

optimum-neuron-cache

dacorvo HF Staff commited on about 1 month ago

Commit

8a334d7

verified ·

1 Parent(s): 28ae1e4

Update inference-cache-config/smollm3.json

Files changed (1) hide show

inference-cache-config/smollm3.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
- "HuggingFaceTB/SmolLM-3B-Instruct": [
    {
       "batch_size": 1,
       "sequence_length": 4096,

 {
+ "HuggingFaceTB/SmolLM-3B": [
    {
       "batch_size": 1,
       "sequence_length": 4096,